© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 5094
    Prev
    Next
    INDEX
    Explanations

    judgment and thinking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pixels
    -0.12
    cola
    -0.11
    -errors
    -0.11
    tica
    -0.11
     Allocate
    -0.11
    uli
    -0.11
     expressive
    -0.11
     PRIV
    -0.11
    iner
    -0.11
     bow
    -0.10
    POSITIVE LOGITS
     discretion
    0.11
    anga
    0.10
     restraint
    0.08
     Ernst
    0.08
    jak
    0.07
     caution
    0.07
     Spar
    0.07
     when
    0.07
     crazy
    0.07
    ately
    0.06
    Activations Density 0.003%

    No Known Activations